What is x-search-plugin AGENTS.md?

Repository instructions for a read-only MCP plugin that lets AI assistants research public posts on X, formerly called Twitter, through xAI’s search service.

Developing or maintaining an X research tool for Codex and Claude Code, with rules for authentication, privacy, and verification.

It defines safe boundaries for research, including no posting or account changes and careful handling of authentication credentials.

How Ilevk/x-search-plugin configures Codex and OpenCode

Reuse

Borrowing it

Nothing to install: this file belongs to Ilevk/x-search-plugin. Take a copy, put it at the same path in your own repository, and replace the rules that are about this project with yours.

Copy the file

curl -O https://raw.githubusercontent.com/Ilevk/x-search-plugin/main/AGENTS.md

Clone the repo

git clone --depth 1 https://github.com/Ilevk/x-search-plugin

Made for: Codex, OpenCode.

Wrote this? Show the measurements

A badge with what this costs and how it scanned, read live from this page, so it follows the numbers instead of freezing them. Markdown for a README, HTML for a documentation site or a project page.

README.md

[![agentmods](https://agentmods.dev/badge/instructions/ilevk/x-search-plugin/agents-md/github.svg)](https://agentmods.dev/instructions/ilevk/x-search-plugin/agents-md)

Your own site

<a href="https://agentmods.dev/instructions/ilevk/x-search-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/ilevk/x-search-plugin/agents-md/github.svg" alt="Measured on agentmods" height="20"></a>

Or the 80×15 button, for a site that already has a row of RSS and ATOM ones. Only the verdict fits; the numbers stay here.

Your own site · 80×15

<a href="https://agentmods.dev/instructions/ilevk/x-search-plugin/agents-md"><img src="https://agentmods.dev/badge/instructions/ilevk/x-search-plugin/agents-md.svg" alt="Reviewed on agentmods" width="80" height="20"></a>

Per session 1,062 This file is loaded in full into every session.

When invoked 1,062 The same file — it is already loaded in full.

Security scan A 0 findings. A grade says what 26 rules found in the file — not that it is safe.

Origin original No closer match found in the catalogue.

Token cost

What it costs to keep this loaded

Counted locally with the o200k_base tokenizer, which is exact for GPT models; Claude uses its own tokenizer and its counts differ. Treat this as one consistent yardstick across the catalogue rather than a bill. Prices are per million input tokens.

Model	Per session	Once invoked
Fable 5.1	$0.01062	$0.01062
Opus 5.5	$0.00425	$0.00425
Sonnet 5.5	$0.00212	$0.00212
Haiku 4.5	$0.00106	$0.00106

Measured 2mo ago against content hash e0aae55d49fa, method: parsed. Prices are Anthropic first-party input rates as of 2026-10-07, from the pricing page.

Security

Grade A, and why

x-search-plugin AGENTS.md scanned grade A with 0 findings against 26 rules in 11 categories — prompt injection, anti-refusal, data exfiltration, privilege escalation, supply chain, agent snooping, system-prompt leakage, SSRF and excessive agency — measured 2mo ago.

A static scan of the body, not an audit. Every finding is printed with the line that produced it so you can judge whether it matters here. A mod is markdown that instructs an agent; that is exactly why what it instructs is worth reading.

Nothing flagged

None of the 26 patterns this scan looks for appear in this file: no shell pipes, no recursive deletes, no credential paths, no hidden text, no instruction-override or anti-refusal phrasing, no agent-config snooping. That is not a guarantee, it is the absence of the things that are checkable.

AGENTS.md · 104 lines

How it starts

The opening of the file, as written. The whole thing — 104 lines — stays where its author put it; the contents beside it link to each section on GitHub.

Repository Agent Guide

Project Goal

This repository provides an MCP plugin for read-only X/Twitter research through xAI's Responses API x_search tool. Codex and Claude Code are the first supported client surfaces.

The primary authentication path is xAI OAuth for entitled X Premium, Premium+, and SuperGrok accounts. XAI_API_KEY remains a fallback path. Do not redesign the project around browser scraping or X API v2 unless Logan explicitly changes the goal.

Boundaries

Must remain read-only: no posting, liking, following, DM access, deletes, or account mutation.
Do not read browser cookies, X app storage, or Hermes credential files.
Do not print, log, commit, or ask the user to paste access tokens, refresh tokens, API keys, or credential file contents. OAuth authorization codes may be pasted only into the local uv run --quiet --locked python scripts/x_search_auth.py login --manual-paste terminal prompt, never into chat or docs. Prefer full callback URLs or ?code=...&state=... fragments over bare authorization codes.
Treat XAI_BASE_URL as a credential sink. Do not use real OAuth/API-key credentials with untrusted override endpoints.
Non-x.ai XAI_BASE_URL with env fallback credentials requires X_SEARCH_ALLOW_UNTRUSTED_BASE_URL=1 and is for local tests only.
OAuth state belongs under ~/.x-search-plugin/auth.json by default, or under X_SEARCH_PLUGIN_HOME when explicitly set.
Legacy ~/.x-search-codex/auth.json and X_SEARCH_CODEX_HOME are supported only for users who authenticated before the project rename.
Keep the implementation dependency-light. The current runtime uses Python standard library only.

Implementation Conventions

Keep MCP protocol behavior in scripts/x_search_mcp.py.
Keep OAuth login, refresh, status, and credential resolution in scripts/xai_oauth.py.
Keep human-facing auth commands in scripts/x_search_auth.py.
Preserve API-key fallback behavior when changing OAuth logic.
Prefer explicit, structured JSON tool results. Missing credentials and upstream failures should return clear tool errors rather than stack traces.
Validate external inputs at the tool boundary. Date ranges should be strict; handle filters should at minimum be normalized, bounded, and kept mutually exclusive where required.

Read the full file on GitHub · 104 lines

Changes

What this file has done since we first saw it

Hashed on every crawl. A supply-chain change to an agent config is a question of when, not whether, so the history is kept rather than the latest state alone.

2mo ago First seen · 104 lines · 1,062 tokens per session scan A e0aae55d49fa

Subscribe to this mod's changes

x-search-plugin AGENTS.md is an instructions file published in the GitHub repository Ilevk/x-search-plugin (0 stars, last pushed 4mo ago), licensed MIT. It adds 1,062 tokens to every session, about $0.0042 per session on Opus 5.5. A static security scan graded it A with 0 findings. No closer match exists in the catalogue, so it is treated as the original; first seen 2026-08-31.

Research

x-search-plugin AGENTS.md next to 6 instructions from other repositories
Mod	Type	Stars	Last push	Licence	Scan	Tokens	Works with
x-search-plugin AGENTS.mdIlevk/x-search-plugin	Instructions file	0	4mo ago	MIT	A	1,062	Codex, OpenCode
vscode buildNext.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	9,719	GitHub Copilot
next.js AGENTS.mdvercel/next.js	Instructions file	143k	yesterday	MIT	A	7,461	Codex, OpenCode
langchain AGENTS.mdlangchain-ai/langchain	Instructions file	149k	yesterday	MIT	A	4,680	Codex, OpenCode
vscode oss-third-party-notices.instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	5,516	GitHub Copilot
vscode copilot-instructions.mdmicrosoft/vscode	Instructions file	195k	yesterday	MIT	A	3,093	GitHub Copilot
deepseek-harness AGENTS.mddeepseek-ai/deepseek-harness	Instructions file	274k	2d ago	MIT	A	4,313	Codex, OpenCode

x-search-plugin: Instructions file for Codex